Yoshua Bengio

Orcid: 0000-0002-9322-3515

Affiliations:
  • University of Montréal, Department of Computer Science and Operations Research, QC, Canada


According to our database1, Yoshua Bengio authored at least 872 papers between 1988 and 2024.

Collaborative distances:

Awards

Turing Prize recipient

Turing Prize 2018, "For conceptual and engineering breakthroughs that have made deep neural networks a critical component of computing." awarded to Yoshua Bengio and Geoffrey E. Hinton and Yann LeCun.

ACM Fellow

ACM Fellow 2023, "For conceptual and engineering breakthroughs that have made deep neural networks a critical component of computing".

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Correction: AI content detection in the emerging information ecosystem: new obligations for media and tech companies.
Ethics Inf. Technol., December, 2024

AI content detection in the emerging information ecosystem: new obligations for media and tech companies.
Ethics Inf. Technol., December, 2024

Distributional GFlowNets with Quantile Flows.
Trans. Mach. Learn. Res., 2024

Multi-Fidelity Active Learning with GFlowNets.
Trans. Mach. Learn. Res., 2024

Improving and generalizing flow-based generative models with minibatch optimal transport.
Trans. Mach. Learn. Res., 2024

PhAST: Physics-Aware, Scalable, and Task-Specific GNNs for Accelerated Catalyst Design.
J. Mach. Learn. Res., 2024

Trajectory Flow Matching with Applications to Clinical Time Series Modeling.
CoRR, 2024

Structure Language Models for Protein Conformation Generation.
CoRR, 2024

Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases.
CoRR, 2024

Action abstractions for amortized sampling.
CoRR, 2024

A Complexity-Based Theory of Compositionality.
CoRR, 2024

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction.
CoRR, 2024

Identifying and Addressing Delusions for Target-Directed Decision-Making.
CoRR, 2024

RL, but don't do anything I wouldn't do.
CoRR, 2024

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models.
CoRR, 2024

Geometric Signatures of Compositionality Across a Language Model's Lifetime.
CoRR, 2024

Adaptive teachers for amortized samplers.
CoRR, 2024

Were RNNs All We Needed?
CoRR, 2024

Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold.
CoRR, 2024

Zero-Shot Object-Centric Representation Learning.
CoRR, 2024

Can a Bayesian Oracle Prevent Harm from an Agent?
CoRR, 2024

Cell Morphology-Guided Small Molecule Generation with GFlowNets.
CoRR, 2024

AI-Assisted Generation of Difficult Math Questions.
CoRR, 2024

Open Problems in Technical AI Governance.
CoRR, 2024

On Generalization for Generative Flow Networks.
CoRR, 2024

RGFN: Synthesizable Molecular Generation Using GFlowNets.
CoRR, 2024

MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation.
CoRR, 2024

VCR: Visual Caption Restoration.
CoRR, 2024

Baking Symmetry into GFlowNets.
CoRR, 2024

Amortizing intractable inference in diffusion models for vision, language, and control.
CoRR, 2024

Learning diverse attacks on large language models for robust red-teaming and safety tuning.
CoRR, 2024

Attention as an RNN.
CoRR, 2024

Divergent Creativity in Humans and Large Language Models.
CoRR, 2024

Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving.
CoRR, 2024

Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems.
CoRR, 2024

Generative Active Learning for the Search of Small-molecule Protein Binders.
CoRR, 2024

Towards DNA-Encoded Library Generation with GFlowNets.
CoRR, 2024

Foundational Challenges in Assuring Alignment and Safety of Large Language Models.
CoRR, 2024

Language Models Can Reduce Asymmetry in Information Markets.
CoRR, 2024

Ant Colony Sampling with GFlowNets for Combinatorial Optimization.
CoRR, 2024

Machine learning and information theory concepts towards an AI Mathematician.
CoRR, 2024

Discrete Probabilistic Inference as Control in Multi-path Environments.
CoRR, 2024

Computing Power and the Governance of Artificial Intelligence.
CoRR, 2024

On diffusion models for amortized inference: Benchmarking and improving stochastic control and sampling.
CoRR, 2024

Efficient Causal Graph Discovery Using Large Language Models.
CoRR, 2024

BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization.
Proceedings of the IEEE International Symposium on Circuits and Systems, 2024

Improving Gradient-Guided Nested Sampling for Posterior Inference.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Learning to Scale Logits for Temperature-Conditional GFlowNets.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Memory Efficient Neural Processes via Constant Memory Attention Block.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Iterated Denoising Energy Matching for Sampling from Boltzmann Densities.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

PhyloGFN: Phylogenetic inference with generative flow networks.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Pre-Training and Fine-Tuning Generative Flow Networks.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Object centric architectures enable efficient causal representation learning.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Local Search GFlowNets.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Expected flow networks in stochastic environments and two-player zero-sum games.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Amortizing intractable inference in large language models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Tree Cross Attention.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Delta-AI: Local objectives for amortized inference in sparse graphical models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Cycle Consistency Driven Object Discovery.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Simulation-Free Schrödinger Bridges via Score and Flow Matching.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

Regeneration Learning: A Learning Paradigm for Data Generation.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Generative AI models should include detection mechanisms as a condition for public release.
Ethics Inf. Technol., December, 2023

DEUP: Direct Epistemic Uncertainty Prediction.
Trans. Mach. Learn. Res., 2023

Neural Causal Structure Discovery from Interventions.
Trans. Mach. Learn. Res., 2023

Scientific discovery in the age of artificial intelligence.
Nat., 2023

Benchmarking Graph Neural Networks.
J. Mach. Learn. Res., 2023

GFlowNet Foundations.
J. Mach. Learn. Res., 2023

Tackling Climate Change with Machine Learning.
ACM Comput. Surv., 2023

A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems.
CoRR, 2023

Shortcut Bias Mitigation via Ensemble Diversity Using Diffusion Probabilistic Models.
CoRR, 2023

Unlearning via Sparse Representations.
CoRR, 2023

SatBird: Bird Species Distribution Modeling with Remote Sensing and Citizen Science Data.
CoRR, 2023

OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning.
CoRR, 2023

Managing AI Risks in an Era of Rapid Progress.
CoRR, 2023

Causal machine learning for single-cell genomics.
CoRR, 2023

Towards equilibrium molecular conformation generation with GFlowNets.
CoRR, 2023

A cry for help: Early detection of brain injury in newborns.
CoRR, 2023

On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions.
CoRR, 2023

Crystal-GFN: sampling crystals with desirable properties and constraints.
CoRR, 2023

Causal Inference in Gene Regulatory Networks with GFlowNet: Towards Scalability in Large Systems.
CoRR, 2023

Learning to Scale Logits for Temperature-Conditional GFlowNets.
CoRR, 2023

Leveraging Diffusion Disentangled Representations to Mitigate Shortcuts in Underspecified Visual Tasks.
CoRR, 2023

Discrete, compositional, and symbolic representations through attractor dynamics.
CoRR, 2023

Combining Spatial and Temporal Abstraction in Planning for Better Generalization.
CoRR, 2023

Consciousness in Artificial Intelligence: Insights from the Science of Consciousness.
CoRR, 2023

AI For Global Climate Cooperation 2023 Competition Proceedings.
CoRR, 2023

Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation.
CoRR, 2023

International Institutions for Advanced AI.
CoRR, 2023

Generative Flow Networks: a Markov Chain Perspective.
CoRR, 2023

Thompson sampling for improved exploration in GFlowNets.
CoRR, 2023

BatchGFN: Generative Flow Networks for Batch Active Learning.
CoRR, 2023

Constant Memory Attention Block.
CoRR, 2023

What if We Enrich day-ahead Solar Irradiance Time Series Forecasting with Spatio-Temporal Context?
CoRR, 2023

Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior.
CoRR, 2023

Attention Schema in Neural Agents.
CoRR, 2023

Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets.
CoRR, 2023

Model evaluation for extreme risks.
CoRR, 2023

Constant Memory Attentive Neural Processes.
CoRR, 2023

Sources of Richness and Ineffability for Phenomenally Conscious States.
CoRR, 2023

DynGFN: Bayesian Dynamic Causal Discovery using Generative Flow Networks.
CoRR, 2023

GFlowNets for AI-Driven Scientific Discovery.
CoRR, 2023

Conditional Flow Matching: Simulation-Free Dynamic Optimal Transport.
CoRR, 2023

Leveraging the Third Dimension in Contrastive Learning.
CoRR, 2023

MixupE: Understanding and improving Mixup from directional derivative perspective.
Proceedings of the Uncertainty in Artificial Intelligence, 2023

Stochastic Generative Flow Networks.
Proceedings of the Uncertainty in Artificial Intelligence, 2023

Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

SatBird: a Dataset for Bird Species Distribution Modeling using Remote Sensing and Citizen Science Data.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Reusable Slotwise Mechanisms.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

GEO-Bench: Toward Foundation Models for Earth Monitoring.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Improving *day-ahead* Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Discrete Key-Value Bottleneck.
Proceedings of the International Conference on Machine Learning, 2023

Hyena Hierarchy: Towards Larger Convolutional Language Models.
Proceedings of the International Conference on Machine Learning, 2023

Better Training of GFlowNets with Local Credit and Incomplete Trajectories.
Proceedings of the International Conference on Machine Learning, 2023

Learning GFlowNets From Partial Episodes For Improved Convergence And Stability.
Proceedings of the International Conference on Machine Learning, 2023

GFlowOut: Dropout with Generative Flow Networks.
Proceedings of the International Conference on Machine Learning, 2023

A theory of continuous generative flow networks.
Proceedings of the International Conference on Machine Learning, 2023

Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning.
Proceedings of the International Conference on Machine Learning, 2023

Equivariance with Learned Canonicalization Functions.
Proceedings of the International Conference on Machine Learning, 2023

Multi-Objective GFlowNets.
Proceedings of the International Conference on Machine Learning, 2023

GFlowNet-EM for Learning Compositional Latent Variable Models.
Proceedings of the International Conference on Machine Learning, 2023

FAENet: Frame Averaging Equivariant GNN for Materials Modeling.
Proceedings of the International Conference on Machine Learning, 2023

Interventional Causal Representation Learning.
Proceedings of the International Conference on Machine Learning, 2023

Robust and Controllable Object-Centric Learning through Energy-based Models.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Latent State Marginalization as a Low-cost Approach for Improving Exploration.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Predictive Inference with Feature Conformal Prediction.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Generative Augmented Flow Networks.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

GFlowNets and variational inference.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Latent Bottlenecked Attentive Neural Processes.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Combining Parameter-efficient Modules for Task-level Generalisation.
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023

Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization for Heterogeneous Representational Coarseness.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

The Effect of Diversity in Meta-Learning.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
A Two-Stream Continual Learning System With Variational Domain-Agnostic Feature Replay.
IEEE Trans. Neural Networks Learn. Syst., 2022

Lookback for Learning to Branch.
Trans. Mach. Learn. Res., 2022

Interpolation consistency training for semi-supervised learning.
Neural Networks, 2022

Interpolated Adversarial Training: Achieving robust neural networks without sacrificing too much accuracy.
Neural Networks, 2022

RetroGNN: Fast Estimation of Synthesizability for Virtual Screening and De Novo Design by Learning from Slow Retrosynthesis Software.
J. Chem. Inf. Model., 2022

Predicting Tactical Solutions to Operational Planning Problems Under Imperfect Information.
INFORMS J. Comput., 2022

MixupE: Understanding and Improving Mixup from Directional Derivative Perspective.
CoRR, 2022

Synergies Between Disentanglement and Sparsity: a Multi-Task Learning Perspective.
CoRR, 2022

Posterior samples of source galaxies in strong gravitational lenses with score-based priors.
CoRR, 2022

Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayes.
CoRR, 2022

A General Purpose Neural Architecture for Geospatial Systems.
CoRR, 2022

Consistent Training via Energy-Based GFlowNets for Modeling Discrete Joint Distributions.
CoRR, 2022

Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning.
CoRR, 2022

FL Games: A Federated Learning Framework for Distribution Shifts.
CoRR, 2022

Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution.
CoRR, 2022

Contrastive introspection (ConSpec) to rapidly identify invariant steps for success.
CoRR, 2022

Graph-Based Active Machine Learning Method for Diverse and Novel Antimicrobial Peptides Generation and Selection.
CoRR, 2022

Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian Optimization.
CoRR, 2022

Unifying Generative Models with GFlowNets.
CoRR, 2022

AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N.
CoRR, 2022

Diversifying Design of Nucleic Acid Aptamers Using Unsupervised Machine Learning.
CoRR, 2022

Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One.
CoRR, 2022

On Neural Architecture Inductive Biases for Relational Tasks.
CoRR, 2022

On the Generalization and Adaption Performance of Causal Models.
CoRR, 2022

Agnostic Physics-Driven Deep Learning.
CoRR, 2022

Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning.
CoRR, 2022

Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel.
CoRR, 2022

FedILC: Weighted Geometric Mean and Invariant Gradient Covariance for Federated Learning on Non-IID Data.
CoRR, 2022

(Private)-Retroactive Carbon Pricing [(P)ReCaP]: A Market-based Approach for Climate Finance and Risk Assessment.
CoRR, 2022

A New Era: Intelligent Tutoring Systems Will Transform Online Learning for Millions.
CoRR, 2022

RECOVER: sequential model optimization platform for combination drug repurposing identifies novel synergistic compounds in vitro.
CoRR, 2022

Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization.
CoRR, 2022

Rethinking Learning Dynamics in RL using Adversarial Networks.
CoRR, 2022

Temporal abstractions-augmented temporally contrastive learning: An alternative to the Laplacian in RL.
Proceedings of the Uncertainty in Artificial Intelligence, 2022

Bayesian structure learning with generative flow networks.
Proceedings of the Uncertainty in Artificial Intelligence, 2022

Neural Attentive Circuits.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Is a Modular Architecture Enough?
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Trajectory balance: Improved credit assignment in GFlowNets.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Discrete Compositional Representations as an Abstraction for Goal Conditioned Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

MAgNet: Mesh Agnostic Neural PDE Solver.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Weakly Supervised Representation Learning with Sparse Perturbations.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Building Robust Ensembles via Margin Boosting.
Proceedings of the International Conference on Machine Learning, 2022

Generative Flow Networks for Discrete Probabilistic Modeling.
Proceedings of the International Conference on Machine Learning, 2022

Multi-scale Feature Learning Dynamics: Insights for Double Descent.
Proceedings of the International Conference on Machine Learning, 2022

Biological Sequence Design with GFlowNets.
Proceedings of the International Conference on Machine Learning, 2022

Towards Scaling Difference Target Propagation by Learning Backprop Targets.
Proceedings of the International Conference on Machine Learning, 2022

Unifying Likelihood-free Inference with Black-box Optimization and Beyond.
Proceedings of the Tenth International Conference on Learning Representations, 2022

ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Chunked Autoregressive GAN for Conditional Waveform Synthesis.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Compositional Attention: Disentangling Search and Retrieval.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Coordination Among Neural Modules Through a Shared Global Workspace.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Graph Neural Networks with Learnable Structural and Positional Representations.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Continuous-Time Meta-Learning with Forward Mode Differentiation.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Properties from mechanisms: an equivariance perspective on identifiable representation learning.
Proceedings of the Tenth International Conference on Learning Representations, 2022

VIM: Variational Independent Modules for Video Prediction.
Proceedings of the 1st Conference on Causal Learning and Reasoning, 2022

PMFL: Partial Meta-Federated Learning for heterogeneous tasks and its applications on real-world medical records.
Proceedings of the IEEE International Conference on Big Data, 2022

2021
CAMAP: Artificial neural networks unveil the role of codon arrangement in modulating MHC-I peptides presentation.
PLoS Comput. Biol., 2021

Toward Causal Representation Learning.
Proc. IEEE, 2021

Inherent privacy limitations of decentralized contact tracing apps.
J. Am. Medical Informatics Assoc., 2021

Machine learning for combinatorial optimization: A methodological tour d'horizon.
Eur. J. Oper. Res., 2021

Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models.
CoRR, 2021

From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence.
CoRR, 2021

Unifying Likelihood-free Inference with Black-box Sequence Design and Beyond.
CoRR, 2021

Learning Neural Causal Models with Active Interventions.
CoRR, 2021

Predicting Unreliable Predictions by Shattering a Neural Network.
CoRR, 2021

Variational Causal Networks: Approximate Bayesian Inference over Causal Structures.
CoRR, 2021

Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization.
CoRR, 2021

SpeechBrain: A General-Purpose Speech Toolkit.
CoRR, 2021

Transformers with Competitive Ensembles of Independent Mechanisms.
CoRR, 2021

Towards Causal Representation Learning.
CoRR, 2021

Structured Sparsity Inducing Adaptive Optimizers for Deep Learning.
CoRR, 2021

Using Artificial Intelligence to Visualize the Impacts of Climate Change.
IEEE Computer Graphics and Applications, 2021

Deep learning for AI.
Commun. ACM, 2021

Exploring the Wasserstein metric for time-to-event analysis.
Proceedings of AAAI Symposium on Survival Prediction, 2021

A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

The Causal-Neural Connection: Expressiveness, Learnability, and Inference.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Dynamic Inference with Neural Interpreters.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Gradient Starvation: A Learning Proclivity in Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Discrete-Valued Neural Communication.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning.
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021

Neural Production Systems.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

hBERT + BiasCorp - Fighting Racism on the Web.
Proceedings of the First Workshop on Language Technology for Equality, 2021

Combating False Negatives in Adversarial Imitation Learning.
Proceedings of the International Joint Conference on Neural Networks, 2021

An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming.
Proceedings of the 38th International Conference on Machine Learning, 2021

Learning Neural Generative Dynamics for Molecular Conformation Generation.
Proceedings of the 9th International Conference on Learning Representations, 2021

Saliency is a Possible Red Herring When Diagnosing Poor Generalization.
Proceedings of the 9th International Conference on Learning Representations, 2021

Spatially Structured Recurrent Modules.
Proceedings of the 9th International Conference on Learning Representations, 2021

RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs.
Proceedings of the 9th International Conference on Learning Representations, 2021

Fast And Slow Learning Of Recurrent Independent Mechanisms.
Proceedings of the 9th International Conference on Learning Representations, 2021

Recurrent Independent Mechanisms.
Proceedings of the 9th International Conference on Learning Representations, 2021

Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments.
Proceedings of the 9th International Conference on Learning Representations, 2021


CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning.
Proceedings of the 9th International Conference on Learning Representations, 2021

Systematic generalisation with group invariant predictions.
Proceedings of the 9th International Conference on Learning Representations, 2021

FloW: A Dataset and Benchmark for Floating Waste Detection in Inland Waters.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

CMIM: Cross-Modal Information Maximization For Medical Imaging.
Proceedings of the IEEE International Conference on Acoustics, 2021

An Analysis of the Adaptation Speed of Causal Models.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

A Comparative Study of Learning Outcomes for Online Learning Platforms.
Proceedings of the Artificial Intelligence in Education - 22nd International Conference, 2021

Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

GraphMix: Improved Training of GNNs for Semi-Supervised Learning.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

Object-Centric Image Generation from Layouts.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

Meta-Learning Framework with Applications to Zero-Shot Time-Series Forecasting.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

Visual Concept Reasoning Networks.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
On the Morality of Artificial Intelligence [Commentary].
IEEE Technol. Soc. Mag., 2020

Toward Training Recurrent Neural Networks for Lifelong Learning.
Neural Comput., 2020

Establishing an evaluation metric to quantify climate change image realism.
Mach. Learn. Sci. Technol., 2020

The Bottleneck Simulator: A Model-Based Deep Reinforcement Learning Approach.
J. Artif. Intell. Res., 2020

Machine Learning for Glacier Monitoring in the Hindu Kush Himalaya.
CoRR, 2020

Inductive Biases for Deep Learning of Higher-Level Cognition.
CoRR, 2020

RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design.
CoRR, 2020

COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing.
CoRR, 2020

NU-GAN: High resolution neural upsampling with GAN.
CoRR, 2020

Cross-Modal Information Maximization for Medical Imaging: CMIM.
CoRR, 2020

Mastering Rate based Curriculum Learning.
CoRR, 2020

Deriving Differential Target Propagation from Iterating Approximate Inverses.
CoRR, 2020

BabyAI 1.1.
CoRR, 2020

S2RMs: Spatially Structured Recurrent Modules.
CoRR, 2020

Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems.
CoRR, 2020

Hybrid Models for Learning to Branch.
CoRR, 2020

Rethinking Distributional Matching Based Domain Adaptation.
CoRR, 2020

Image-to-image Mapping with Many Domains by Sparse Attribute Transfer.
CoRR, 2020

HNHN: Hypergraph Networks with Hyperedge Neurons.
CoRR, 2020

Untangling tradeoffs between recurrence and self-attention in neural networks.
CoRR, 2020

Learning Causal Models Online.
CoRR, 2020

Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias.
CoRR, 2020

Training End-to-End Analog Neural Networks with Equilibrium Propagation.
CoRR, 2020

Predicting COVID-19 Pneumonia Severity on Chest X-ray with Deep Learning.
CoRR, 2020

COVI White Paper.
CoRR, 2020

Continual Weight Updates and Convolutional Architectures for Equilibrium Propagation.
CoRR, 2020

Equilibrium Propagation with Continual Weight Updates.
CoRR, 2020

Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims.
CoRR, 2020

Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay.
CoRR, 2020

Benchmarking Graph Neural Networks.
CoRR, 2020

On Catastrophic Interference in Atari 2600 Games.
CoRR, 2020

Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning.
CoRR, 2020

HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagery.
CoRR, 2020

BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization.
CoRR, 2020

Using Simulated Data to Generate Images of Climate Change.
CoRR, 2020

Universal Successor Features for Transfer Reinforcement Learning.
CoRR, 2020

Learning from Learning Machines: Optimisation, Rules, and Social Norms.
CoRR, 2020

Generative adversarial networks.
Commun. ACM, 2020

Factorized embeddings learns rich and biologically meaningful embedding spaces using factorized tensor decomposition.
Bioinform., 2020

Joint Learning of Generative Translator and Classifier for Visually Similar Classes.
IEEE Access, 2020

Untangling tradeoffs between recurrence and self-attention in artificial neural networks.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Hybrid Models for Learning to Branch.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Quantized Guided Pruning for Efficient Hardware Implementations of Deep Neural Networks.
Proceedings of the 18th IEEE International New Circuits and Systems Conference, 2020

Attention Based Pruning for Shift Networks.
Proceedings of the 25th International Conference on Pattern Recognition, 2020

Perceptual Generative Autoencoders.
Proceedings of the 37th International Conference on Machine Learning, 2020

Small-GAN: Speeding up GAN Training using Core-Sets.
Proceedings of the 37th International Conference on Machine Learning, 2020

Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules.
Proceedings of the 37th International Conference on Machine Learning, 2020

Learning to Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning.
Proceedings of the 37th International Conference on Machine Learning, 2020

Revisiting Fundamentals of Experience Replay.
Proceedings of the 37th International Conference on Machine Learning, 2020

Learning the Arrow of Time for Problems in Reinforcement Learning.
Proceedings of the 8th International Conference on Learning Representations, 2020

N-BEATS: Neural basis expansion analysis for interpretable time series forecasting.
Proceedings of the 8th International Conference on Learning Representations, 2020

Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives.
Proceedings of the 8th International Conference on Learning Representations, 2020

The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget.
Proceedings of the 8th International Conference on Learning Representations, 2020

A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms.
Proceedings of the 8th International Conference on Learning Representations, 2020

Multi-Task Self-Supervised Learning for Robust Speech Recognition.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Experience Grounds Language.
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020

DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning.
Proceedings of the Computer Vision - ECCV 2020, 2020

Multi-Image Super-Resolution for Remote Sensing using Deep Recurrent Networks.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

A Learning-Based Algorithm to Quickly Compute Good Primal Solutions for Stochastic Integer Programs.
Proceedings of the Integration of Constraint Programming, Artificial Intelligence, and Operations Research, 2020

Systematicity in a Recurrent Neural Network by Factorizing Syntax and Semantics.
Proceedings of the 42th Annual Meeting of the Cognitive Science Society, 2020

On the interplay between noise and curvature and its effect on optimization and generalization.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM.
Proceedings of the Artificial Intelligence in Education - 21st International Conference, 2020

Compositional Generalization by Factorizing Alignment and Translation.
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, 2020

Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach.
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020

Combating False Negatives in Adversarial Imitation Learning (Student Abstract).
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
Depth with nonlinearity creates no bad local minima in ResNets.
Neural Networks, 2019

Equivalence of Equilibrium Propagation and Recurrent Backpropagation.
Neural Comput., 2019

Gated Orthogonal Recurrent Units: On Learning to Forget.
Neural Comput., 2019

On the Morality of Artificial Intelligence.
CoRR, 2019

CLOSURE: Assessing Systematic Generalization of CLEVR Models.
CoRR, 2019

The effect of task and training on intermediate representations in convolutional neural networks revealed with modified RV similarity analysis.
CoRR, 2019

Applying Knowledge Transfer for Water Body Segmentation in Peru.
CoRR, 2019

Automated curriculum generation for Policy Gradients from Demonstrations.
CoRR, 2019

Ghost Units Yield Biologically Plausible Backprop in Deep Neural Networks.
CoRR, 2019

Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery.
CoRR, 2019

Predicting ice flow using machine learning.
CoRR, 2019

Learning Neural Causal Models from Unknown Interventions.
CoRR, 2019

Underwhelming Generalization Improvements From Controlling Feature Attribution.
CoRR, 2019

GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning.
CoRR, 2019

Avoidance Learning Using Observational Reinforcement Learning.
CoRR, 2019

Torchmeta: A Meta-Learning library for PyTorch.
CoRR, 2019

Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures.
CoRR, 2019

Weakly-supervised Knowledge Graph Alignment with Adversarial Learning.
CoRR, 2019

Learning the Arrow of Time.
CoRR, 2019

Information matrices and generalization.
CoRR, 2019

Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Accuracy.
CoRR, 2019

Conditional Computation for Continual Learning.
CoRR, 2019

Learning Powerful Policies by Using Consistent Dynamics Model.
CoRR, 2019

State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations.
CoRR, 2019

The Journey is the Reward: Unsupervised Learning of Influential Trajectories.
CoRR, 2019

Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networks.
CoRR, 2019

Compositional generalization in a deep seq2seq model by separating syntax and semantics.
CoRR, 2019

GradMask: Reduce Overfitting by Regularizing Saliency.
CoRR, 2019

Reinforced Imitation in Heterogeneous Action Space.
CoRR, 2019

Towards Standardization of Data Licenses: The Montreal Data License.
CoRR, 2019

Online continual learning with no task boundaries.
CoRR, 2019

Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future.
CoRR, 2019

Hyperbolic Discounting and Learning over Multiple Horizons.
CoRR, 2019

Maximum Entropy Generators for Energy-Based Models.
CoRR, 2019

The Benefits of Over-parameterization at Initialization in Deep ReLU Networks.
CoRR, 2019

Wasserstein Dependency Measure for Representation Learning.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Variational Temporal Abstraction.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

On Adversarial Mixup Resynthesis.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

How to Initialize your Network? Robust Initialization for WeightNorm & ResNets.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Unsupervised State Representation Learning in Atari.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Gradient based sample selection for online continual learning.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

InfoMask: Masked Variational Latent Representation to Localize Chest Disease.
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2019, 2019

Learning Speaker Representations with Mutual Information.
Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Learning Problem-Agnostic Speech Representations from Multiple Self-Supervised Tasks.
Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Speech Model Pre-Training for End-to-End Spoken Language Understanding.
Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Interpolation Consistency Training for Semi-supervised Learning.
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019

A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies.
Proceedings of the International Conference on Robotics and Automation, 2019

Manifold Mixup: Better Representations by Interpolating Hidden States.
Proceedings of the 36th International Conference on Machine Learning, 2019

On the Spectral Bias of Neural Networks.
Proceedings of the 36th International Conference on Machine Learning, 2019

GMNN: Graph Markov Neural Networks.
Proceedings of the 36th International Conference on Machine Learning, 2019

State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations.
Proceedings of the 36th International Conference on Machine Learning, 2019

Deep Graph Infomax.
Proceedings of the 7th International Conference on Learning Representations, 2019

An Empirical Study of Example Forgetting during Deep Neural Network Learning.
Proceedings of the 7th International Conference on Learning Representations, 2019

Probabilistic Planning with Sequential Monte Carlo methods.
Proceedings of the 7th International Conference on Learning Representations, 2019

Quaternion Recurrent Neural Networks.
Proceedings of the 7th International Conference on Learning Representations, 2019

Modeling the Long Term Future in Model-Based Reinforcement Learning.
Proceedings of the 7th International Conference on Learning Representations, 2019

h-detach: Modifying the LSTM Gradient Towards Better Optimization.
Proceedings of the 7th International Conference on Learning Representations, 2019

On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length.
Proceedings of the 7th International Conference on Learning Representations, 2019

Learning deep representations by mutual information estimation and maximization.
Proceedings of the 7th International Conference on Learning Representations, 2019

InfoBot: Transfer and Exploration via the Information Bottleneck.
Proceedings of the 7th International Conference on Learning Representations, 2019

Recall Traces: Backtracking Models for Efficient Reinforcement Learning.
Proceedings of the 7th International Conference on Learning Representations, 2019

Adversarial Domain Adaptation for Stable Brain-Machine Interfaces.
Proceedings of the 7th International Conference on Learning Representations, 2019

BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning.
Proceedings of the 7th International Conference on Learning Representations, 2019

Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and Localization.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

A Highly Adaptive Acoustic Model for Accurate Multi-dialect Speech Recognition.
Proceedings of the IEEE International Conference on Acoustics, 2019

How Transferable Are Features in Convolutional Neural Network Acoustic Models across Languages?
Proceedings of the IEEE International Conference on Acoustics, 2019

The Pytorch-kaldi Speech Recognition Toolkit.
Proceedings of the IEEE International Conference on Acoustics, 2019

Representation Mixing for TTS Synthesis.
Proceedings of the IEEE International Conference on Acoustics, 2019

Interactive Language Learning by Question Answering.
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019

Interpolated Adversarial Training: Achieving Robust Neural Networks Without Sacrificing Too Much Accuracy.
Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security, 2019

Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study.
Proceedings of the 57th Conference of the Association for Computational Linguistics, 2019

Combined Reinforcement Learning via Abstract Representations.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

Towards Non-Saturating Recurrent Units for Modelling Long-Term Dependencies.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

2018
Light Gated Recurrent Units for Speech Recognition.
IEEE Trans. Emerg. Top. Comput. Intell., 2018

Drawing and Recognizing Chinese Characters with Recurrent Neural Network.
IEEE Trans. Pattern Anal. Mach. Intell., 2018

Dynamic Neural Turing Machine with Continuous and Discrete Addressing Schemes.
Neural Comput., 2018

Learning normalized inputs for iterative estimation in medical image segmentation.
Medical Image Anal., 2018

Fine-grained attention mechanism for neural machine translation.
Neurocomputing, 2018

Quantized Guided Pruning for Efficient Hardware Implementations of Convolutional Neural Networks.
CoRR, 2018

Speech and Speaker Recognition from Raw Waveform with SincNet.
CoRR, 2018

The effects of negative adaptation in Model-Agnostic Meta-Learning.
CoRR, 2018

Keep Drawing It: Iterative language-based image generation and editing.
CoRR, 2018

DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation.
CoRR, 2018

Interpretable Convolutional Filters with SincNet.
CoRR, 2018

On Training Recurrent Neural Networks for Lifelong Learning.
CoRR, 2018

How can deep learning advance computational modeling of sensory information processing?
CoRR, 2018

BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop.
CoRR, 2018

Towards the Latent Transcriptome.
CoRR, 2018

On the Learning Dynamics of Deep Neural Networks.
CoRR, 2018

Sparse Attentive Backtracking: Temporal CreditAssignment Through Reminding.
CoRR, 2018

Learning deep representations by mutual information estimation and maximization.
CoRR, 2018

Generalization of Equilibrium Propagation to Vector Field Dynamics.
CoRR, 2018

Predicting Solution Summaries to Integer Linear Programs under Imperfect Information with Machine Learning.
CoRR, 2018

DNN's Sharpest Directions Along the SGD Trajectory.
CoRR, 2018

On the Spectral Bias of Deep Neural Networks.
CoRR, 2018

Towards Gene Expression Convolutions using Gene Interaction Graphs.
CoRR, 2018

Modularity Matters: Learning Invariant Relational Reasoning Tasks.
CoRR, 2018

Manifold Mixup: Encouraging Meaningful On-Manifold Interpolation as a Regularizer.
CoRR, 2018

Learning to rank for censored survival data.
CoRR, 2018

Low-memory convolutional neural networks through incremental depth-first processing.
CoRR, 2018

Commonsense mining as knowledge base completion? A study on the impact of novelty.
CoRR, 2018

Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations.
CoRR, 2018

Recall Traces: Backtracking Models for Efficient Reinforcement Learning.
CoRR, 2018

Disentangling the independently controllable factors of variation by interacting with the world.
CoRR, 2018

Learning Anonymized Representations with Adversarial Neural Networks.
CoRR, 2018

A Walk with SGD.
CoRR, 2018

Generalization in Machine Learning via Analytical Learning Theory.
CoRR, 2018

A Deep Reinforcement Learning Chatbot (Short Version).
CoRR, 2018

A3T: Adversarially Augmented Adversarial Training.
CoRR, 2018

ObamaNet: Photo-realistic lip-sync from text.
CoRR, 2018

Dendritic error backpropagation in deep cortical microcircuits.
CoRR, 2018

Deep convolutional networks for quality assessment of protein folds.
Bioinform., 2018

Speaker Recognition from Raw Waveform with SincNet.
Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

Learning Hierarchical Structures On-The-Fly with a Recurrent-Recursive Model for Sequences.
Proceedings of The Third Workshop on Representation Learning for NLP, 2018

MetaGAN: An Adversarial Approach to Few-Shot Learning.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Bayesian Model-Agnostic Meta-Learning.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Dendritic cortical microcircuits approximate the backpropagation algorithm.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Image-to-image translation for cross-domain disentanglement.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Twin Regularization for Online Speech Recognition.
Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition.
Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation.
Proceedings of the 2018 International Joint Conference on Neural Networks, 2018

Focused Hierarchical RNNs for Conditional Sequence Processing.
Proceedings of the 35th International Conference on Machine Learning, 2018

Mutual Information Neural Estimation.
Proceedings of the 35th International Conference on Machine Learning, 2018

Fraternal Dropout.
Proceedings of the 6th International Conference on Learning Representations, 2018

Graph Attention Networks.
Proceedings of the 6th International Conference on Learning Representations, 2018

Deep Complex Networks.
Proceedings of the 6th International Conference on Learning Representations, 2018

Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning.
Proceedings of the 6th International Conference on Learning Representations, 2018

ChatPainter: Improving Text to Image Generation using Dialogue.
Proceedings of the 6th International Conference on Learning Representations, 2018

Twin Networks: Matching the Future for Sequence Generation.
Proceedings of the 6th International Conference on Learning Representations, 2018

Extending the Framework of Equilibrium Propagation to General Dynamics.
Proceedings of the 6th International Conference on Learning Representations, 2018

Universal Successor Representations for Transfer Reinforcement Learning.
Proceedings of the 6th International Conference on Learning Representations, 2018

FigureQA: An Annotated Figure Dataset for Visual Reasoning.
Proceedings of the 6th International Conference on Learning Representations, 2018

Finding Flatter Minima with SGD.
Proceedings of the 6th International Conference on Learning Representations, 2018

Residual Connections Encourage Iterative Inference.
Proceedings of the 6th International Conference on Learning Representations, 2018

Boundary Seeking GANs.
Proceedings of the 6th International Conference on Learning Representations, 2018

Dynamic Frame Skipping for Fast Speech Recognition in Recurrent Neural Network Based Acoustic Models.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Towards End-to-end Spoken Language Understanding.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio.
Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2018, 2018

HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering.
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October 31, 2018

On the Iterative Refinement of Densely Connected Representation Levels for Semantic Segmentation.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018

Neural Models for Key Phrase Extraction and Question Generation.
Proceedings of the Workshop on Machine Reading for Question Answering@ACL 2018, 2018

Straight to the Tree: Constituency Parsing with Neural Syntactic Distance.
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018

2017
End-to-End Online Writer Identification With Recurrent Neural Network.
IEEE Trans. Hum. Mach. Syst., 2017

Online and offline handwritten Chinese character recognition: A comprehensive study and new benchmark.
Pattern Recognit., 2017

STDP-Compatible Approximation of Backpropagation in an Energy-Based Model.
Neural Comput., 2017

The representational geometry of word meanings acquired by neural machine translation models.
Mach. Transl., 2017

Brain tumor segmentation with Deep Neural Networks.
Medical Image Anal., 2017

Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations.
J. Mach. Learn. Res., 2017

Equilibrium Propagation: Bridging the Gap between Energy-Based Models and Backpropagation.
Frontiers Comput. Neurosci., 2017

On integrating a language model into neural machine translation.
Comput. Speech Lang., 2017

Multi-way, multilingual neural machine translation.
Comput. Speech Lang., 2017

Context-dependent word representation for neural machine translation.
Comput. Speech Lang., 2017

Measuring the tendency of CNNs to Learn Surface Statistical Regularities.
CoRR, 2017

Variational Bi-LSTMs.
CoRR, 2017

ACtuAL: Actor-Critic Under Adversarial Learning.
CoRR, 2017

Three Factors Influencing Minima in SGD.
CoRR, 2017

Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks.
CoRR, 2017

Generalization in Deep Learning.
CoRR, 2017

The Consciousness Prior.
CoRR, 2017

A Deep Reinforcement Learning Chatbot.
CoRR, 2017

Twin Networks: Using the Future as a Regularizer.
CoRR, 2017

Independently Controllable Factors.
CoRR, 2017

Deep Complex Networks.
CoRR, 2017

Image Segmentation by Iterative Inference from Conditional Score Estimation.
CoRR, 2017

Multiscale sequence modeling with a learned dictionary.
CoRR, 2017

Deep Learning for Patient-Specific Kidney Graft Survival Analysis.
CoRR, 2017

Boundary-Seeking Generative Adversarial Networks.
CoRR, 2017

Plan, Attend, Generate: Character-level Neural Machine Translation with Planning in the Decoder.
CoRR, 2017

Memory Augmented Neural Networks with Wormhole Connections.
CoRR, 2017

Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation.
CoRR, 2017

Count-ception: Counting by Fully Convolutional Redundant Counting.
CoRR, 2017

Maximum-Likelihood Augmented Discrete Generative Adversarial Networks.
CoRR, 2017

Independently Controllable Features.
CoRR, 2017

Learning to Compute Word Embeddings On the Fly.
CoRR, 2017

Plan, Attend, Generate: Character-Level Neural Machine Translation with Planning.
Proceedings of the 2nd Workshop on Representation Learning for NLP, 2017

GibbsNet: Iterative Adversarial Inference for Deep Graphical Models.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Plan, Attend, Generate: Planning for Sequence-to-Sequence Models.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Z-Forcing: Training Stochastic Recurrent Networks.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Towards more hardware-friendly deep learning.
Proceedings of the Workshop on Trends in Machine-Learning (and impact on computer architecture), 2017

Improving Speech Recognition by Revising Gated Recurrent Units.
Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition.
Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

A robust adaptive stochastic gradient method for deep learning.
Proceedings of the 2017 International Joint Conference on Neural Networks, 2017

Sharp Minima Can Generalize For Deep Nets.
Proceedings of the 34th International Conference on Machine Learning, 2017

A Closer Look at Memorization in Deep Networks.
Proceedings of the 34th International Conference on Machine Learning, 2017

Improving Generative Adversarial Networks with Denoising Feature Matching.
Proceedings of the 5th International Conference on Learning Representations, 2017

Char2Wav: End-to-End Speech Synthesis.
Proceedings of the 5th International Conference on Learning Representations, 2017

Diet Networks: Thin Parameters for Fat Genomics.
Proceedings of the 5th International Conference on Learning Representations, 2017

Generalizable Features From Unsupervised Learning.
Proceedings of the 5th International Conference on Learning Representations, 2017

SampleRNN: An Unconditional End-to-End Neural Audio Generation Model.
Proceedings of the 5th International Conference on Learning Representations, 2017

Towards an automatic Turing test: Learning to evaluate dialogue responses.
Proceedings of the 5th International Conference on Learning Representations, 2017

A Structured Self-Attentive Sentence Embedding.
Proceedings of the 5th International Conference on Learning Representations, 2017

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations.
Proceedings of the 5th International Conference on Learning Representations, 2017

Mollifying Networks.
Proceedings of the 5th International Conference on Learning Representations, 2017

Hierarchical Multiscale Recurrent Neural Networks.
Proceedings of the 5th International Conference on Learning Representations, 2017

Mode Regularized Generative Adversarial Networks.
Proceedings of the 5th International Conference on Learning Representations, 2017

An Actor-Critic Algorithm for Sequence Prediction.
Proceedings of the 5th International Conference on Learning Representations, 2017

Understanding intermediate layers using linear classifier probes.
Proceedings of the 5th International Conference on Learning Representations, 2017

Count-ception: Counting by Fully Convolutional Redundant Counting.
Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops, 2017

A network of deep neural networks for Distant Speech Recognition.
Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

On random weights for texture generation in one layer CNNS.
Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017

A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues.
Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation.
Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

Denoising Criterion for Variational Auto-Encoding Framework.
Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

2016
Learning to Understand Phrases by Embedding the Dictionary.
Trans. Assoc. Comput. Linguistics, 2016

Big Data: Theoretical Aspects [Scanning the Issue].
Proc. IEEE, 2016

EmoNets: Multimodal deep learning approaches for emotion recognition in video.
J. Multimodal User Interfaces, 2016

Iterative Alternating Neural Attention for Machine Reading.
CoRR, 2016

Invariant Representations for Noisy Speech Recognition.
CoRR, 2016

Towards a Biologically Plausible Backprop.
CoRR, 2016

Diet Networks: Thin Parameters for Fat Genomic.
CoRR, 2016

Recurrent Neural Networks With Limited Numerical Precision.
CoRR, 2016

On Random Weights for Texture Generation in One Layer Neural Networks.
CoRR, 2016

Neural Networks with Few Multiplications.
Proceedings of the 4th International Conference on Learning Representations, 2016

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations.
CoRR, 2016

Deep Directed Generative Models with Energy-Based Probability Estimation.
CoRR, 2016

Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes.
CoRR, 2016

BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1.
CoRR, 2016

Hierarchical Memory Networks.
CoRR, 2016

Feedforward Initialization for Fast Inference of Deep Generative Networks is biologically plausible.
CoRR, 2016

Theano: A Python framework for fast computation of mathematical expressions.
, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,
CoRR, 2016

A Neural Knowledge Language Model.
CoRR, 2016

NYU-MILA Neural Machine Translation Systems for WMT'16.
Proceedings of the First Conference on Machine Translation, 2016

Batch-normalized joint training for DNN-based distant speech recognition.
Proceedings of the 2016 IEEE Spoken Language Technology Workshop, 2016

Architectural Complexity Measures of Recurrent Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

On Multiplicative Integration with Recurrent Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Binarized Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Professor Forcing: A New Algorithm for Training Recurrent Networks.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism.
Proceedings of the NAACL HLT 2016, 2016

HeMIS: Hetero-Modal Image Segmentation.
Proceedings of the Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016, 2016

Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks.
Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

Deconstructing the Ladder Network Architecture.
Proceedings of the 33nd International Conference on Machine Learning, 2016

Noisy Activation Functions.
Proceedings of the 33nd International Conference on Machine Learning, 2016

Bidirectional Helmholtz Machines.
Proceedings of the 33nd International Conference on Machine Learning, 2016

Unitary Evolution Recurrent Neural Networks.
Proceedings of the 33nd International Conference on Machine Learning, 2016

Batch normalized recurrent neural networks.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

End-to-end attention-based large vocabulary speech recognition.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

ReSeg: A Recurrent Neural Network-Based Model for Semantic Segmentation.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2016

Oracle Performance for Visual Captioning.
Proceedings of the British Machine Vision Conference 2016, 2016

Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus.
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016

Pointing the Unknown Words.
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016

A Character-level Decoder without Explicit Segmentation for Neural Machine Translation.
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016

Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models.
Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016

Deep Learning.
Adaptive computation and machine learning, MIT Press, ISBN: 978-0-262-03561-3, 2016

2015
Describing Multimedia Content Using Attention-Based Encoder-Decoder Networks.
IEEE Trans. Multim., 2015

Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding.
IEEE ACM Trans. Audio Speech Lang. Process., 2015

Challenges in representation learning: A report on three machine learning contests.
Neural Networks, 2015

Editorial introduction to the Neural Networks special issue on Deep Learning of Representations.
Neural Networks, 2015

Deep learning.
Nat., 2015

Trainable performance upper bounds for image and video captioning.
CoRR, 2015

ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks.
CoRR, 2015

ReSeg: A Recurrent Neural Network for Object Segmentation.
CoRR, 2015

Hierarchical Neural Network Generative Models for Movie Dialogues.
CoRR, 2015

FitNets: Hints for Thin Deep Nets.
Proceedings of the 3rd International Conference on Learning Representations, 2015

Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews.
Proceedings of the 3rd International Conference on Learning Representations, 2015

Blocks and Fuel: Frameworks for deep learning.
CoRR, 2015

Target Propagation.
Proceedings of the 3rd International Conference on Learning Representations, 2015

Embedding Word Similarity with Neural Machine Translation.
Proceedings of the 3rd International Conference on Learning Representations, 2015

On Using Monolingual Corpora in Neural Machine Translation.
CoRR, 2015

NICE: Non-linear Independent Components Estimation.
Proceedings of the 3rd International Conference on Learning Representations, 2015

RMSProp and equilibrated adaptive learning rates for non-convex optimization.
CoRR, 2015

Low precision arithmetic for deep learning.
Proceedings of the 3rd International Conference on Learning Representations, 2015

Training opposing directed models using geometric mean matching.
CoRR, 2015

Reweighted Wake-Sleep.
Proceedings of the 3rd International Conference on Learning Representations, 2015

An objective function for STDP.
CoRR, 2015

Towards Biologically Plausible Deep Learning.
CoRR, 2015

Early Inference in Energy-Based Models Approximates Back-Propagation.
CoRR, 2015

Task Loss Estimation for Sequence Prediction.
CoRR, 2015

Neural Machine Translation by Jointly Learning to Align and Translate.
Proceedings of the 3rd International Conference on Learning Representations, 2015

Variance Reduction in SGD by Distributed Importance Sampling.
CoRR, 2015

GSNs : Generative Stochastic Networks.
CoRR, 2015

Montreal Neural Machine Translation Systems for WMT'15.
Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015

Difference Target Propagation.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2015

Artificial Neural Networks Applied to Taxi Destination Prediction.
Proceedings of the ECML/PKDD 2015 Discovery Challenges co-located with European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2015), 2015

Equilibrated adaptive learning rates for non-convex optimization.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

BinaryConnect: Training Deep Neural Networks with binary weights during propagations.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

A Recurrent Latent Variable Model for Sequential Data.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Attention-Based Models for Speech Recognition.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention.
Proceedings of the 32nd International Conference on Machine Learning, 2015

BilBOWA: Fast Bilingual Distributed Representations without Word Alignments.
Proceedings of the 32nd International Conference on Machine Learning, 2015

Gated Feedback Recurrent Neural Networks.
Proceedings of the 32nd International Conference on Machine Learning, 2015

A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion.
Proceedings of the 24th ACM International Conference on Information and Knowledge Management, 2015

IAPR keynote lecture IV: Deep learning.
Proceedings of the 3rd IAPR Asian Conference on Pattern Recognition, 2015

On Using Very Large Target Vocabulary for Neural Machine Translation.
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, 2015

2014
Evolving Culture Versus Local Minima.
Proceedings of the Growing Adaptive Machines, 2014

The Spike-and-Slab RBM and Extensions to Discrete and Sparse Data Distributions.
IEEE Trans. Pattern Anal. Mach. Intell., 2014

Learning semantic representations of objects and their parts.
Mach. Learn., 2014

A semantic matching energy function for learning with multi-relational data - Application to word-sense disambiguation.
Mach. Learn., 2014

What regularized auto-encoders learn from the data-generating distribution.
J. Mach. Learn. Res., 2014

Revisiting Natural Gradient for Deep Networks
Proceedings of the 2nd International Conference on Learning Representations, 2014

An empirical analysis of dropout in piecewise linear networks.
Proceedings of the 2nd International Conference on Learning Representations, 2014

On the number of inference regions of deep feed forward networks with piece-wise linear activations.
Proceedings of the 2nd International Conference on Learning Representations, 2014

How to Construct Deep Recurrent Neural Networks.
Proceedings of the 2nd International Conference on Learning Representations, 2014

On the saddle point problem for non-convex optimization.
CoRR, 2014

Multimodal Transitions for Generative Stochastic Networks.
Proceedings of the 2nd International Conference on Learning Representations, 2014

Deep Directed Generative Autoencoders.
CoRR, 2014

Not All Neural Embeddings are Born Equal.
CoRR, 2014

ADASECANT: Robust Adaptive Secant Method for Stochastic Gradient.
CoRR, 2014

An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks.
Proceedings of the 2nd International Conference on Learning Representations, 2014

Deep Tempering.
CoRR, 2014

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling.
CoRR, 2014

End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results.
CoRR, 2014

Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation.
CoRR, 2014

Exponentially Increasing the Capacity-to-Computation Ratio for Conditional Computation in Deep Learning.
CoRR, 2014

Bounding the Test Log-Likelihood of Generative Models.
Proceedings of the 2nd International Conference on Learning Representations, 2014

How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation.
CoRR, 2014

Conditioning and time representation in long short-term memory networks.
Biol. Cybern., 2014

Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation.
Proceedings of SSST@EMNLP 2014, 2014

On the Properties of Neural Machine Translation: Encoder-Decoder Approaches.
Proceedings of SSST@EMNLP 2014, 2014

On the Equivalence between Deep NADE and Generative Stochastic Networks.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2014

Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2014

How transferable are features in deep neural networks?
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Iterative Neural Autoregressive Distribution Estimator NADE-k.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

On the Number of Linear Regions of Deep Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Generative Adversarial Nets.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Identifying and attacking the saddle point problem in high-dimensional non-convex optimization.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Scaling up deep learning.
Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014

Marginalized Denoising Auto-encoders for Nonlinear Representations.
Proceedings of the 31th International Conference on Machine Learning, 2014

Deep Generative Stochastic Networks Trainable by Backprop.
Proceedings of the 31th International Conference on Machine Learning, 2014

Deep learning and cultural evolution.
Proceedings of the Genetic and Evolutionary Computation Conference, 2014

Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation.
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, 2014

Learning Concept Embeddings for Query Expansion by Quantum Entropy Minimization.
Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, 2014

On the Challenges of Physical Implementations of RBMs.
Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, 2014

2013
Deep Learning of Representations.
Proceedings of the Handbook on Neural Information Processing, 2013

Scaling Up Spike-and-Slab Models for Unsupervised Feature Learning.
IEEE Trans. Pattern Anal. Mach. Intell., 2013

Representation Learning: A Review and New Perspectives.
IEEE Trans. Pattern Anal. Mach. Intell., 2013

Estimating or Propagating Gradients Through Stochastic Neurons
CoRR, 2013

Knowledge Matters: Importance of Prior Information for Optimization
Proceedings of the 1st International Conference on Learning Representations, 2013

Natural Gradient Revisited
Proceedings of the 1st International Conference on Learning Representations, 2013

Big Neural Networks Waste Capacity
Proceedings of the 1st International Conference on Learning Representations, 2013

Joint Training Deep Boltzmann Machines for Classification
Proceedings of the 1st International Conference on Learning Representations, 2013

Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines
Proceedings of the 1st International Conference on Learning Representations, 2013

A Semantic Matching Energy Function for Learning with Multi-relational Data
Proceedings of the 1st International Conference on Learning Representations, 2013

Regularized Auto-Encoders Estimate Local Statistics
Proceedings of the 1st International Conference on Learning Representations, 2013

Learned-norm pooling for deep neural networks.
CoRR, 2013

Pylearn2: a machine learning research library.
CoRR, 2013

Deep Generative Stochastic Networks Trainable by Backprop.
CoRR, 2013

Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.
CoRR, 2013

Learning Deep Physiological Models of Affect.
IEEE Comput. Intell. Mag., 2013

Deep Learning of Representations: Looking Forward.
Proceedings of the Statistical Language and Speech Processing, 2013

Modeling term dependencies with quantum language models for IR.
Proceedings of the 36th International ACM SIGIR conference on research and development in Information Retrieval, 2013

Multi-Prediction Deep Boltzmann Machines.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Stochastic Ratio Matching of RBMs for Sparse High-Dimensional Inputs.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Generalized Denoising Auto-Encoders as Generative Models.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Audio Chord Recognition with Recurrent Neural Networks.
Proceedings of the 14th International Society for Music Information Retrieval Conference, 2013

Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding.
Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Unsupervised Learning of Semantics of Object Detections for Scene Categorization.
Proceedings of the Pattern Recognition Applications and Methods - International Conference, 2013

Unsupervised and Transfer Learning under Uncertainty - From Object Detections to Scene Categorization.
Proceedings of the ICPRAM 2013, 2013


On the difficulty of training recurrent neural networks.
Proceedings of the 30th International Conference on Machine Learning, 2013

Maxout Networks.
Proceedings of the 30th International Conference on Machine Learning, 2013

Better Mixing via Deep Representations.
Proceedings of the 30th International Conference on Machine Learning, 2013


High-dimensional sequence transduction.
Proceedings of the IEEE International Conference on Acoustics, 2013

Advances in optimizing recurrent networks.
Proceedings of the IEEE International Conference on Acoustics, 2013

Stacked calibration of off-policy policy evaluation for video game matchmaking.
Proceedings of the 2013 IEEE Conference on Computational Inteligence in Games (CIG), 2013

Texture Modeling with Convolutional Spike-and-Slab RBMs and Deep Extensions.
Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics, 2013

2012
Practical Recommendations for Gradient-Based Training of Deep Architectures.
Proceedings of the Neural Networks: Tricks of the Trade - Second Edition, 2012

Beyond Skill Rating: Advanced Matchmaking in Ghost Recon Online.
IEEE Trans. Comput. Intell. AI Games, 2012

Unsupervised and Transfer Learning Challenge: a Deep Learning Approach.
Proceedings of the Unsupervised and Transfer Learning, 2012

Learning Algorithms for the Classification Restricted Boltzmann Machine.
J. Mach. Learn. Res., 2012

Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing.
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, 2012

Random Search for Hyper-Parameter Optimization.
J. Mach. Learn. Res., 2012

Deep Learning of Representations for Unsupervised and Transfer Learning.
Proceedings of the Unsupervised and Transfer Learning, 2012

Joint Training of Deep Boltzmann Machines
CoRR, 2012

Theano: new features and speed improvements
CoRR, 2012

Understanding the exploding gradient problem
CoRR, 2012

Disentangling Factors of Variation via Generative Entangling
CoRR, 2012

Efficient EM Training of Gaussian Mixtures with Missing Data
CoRR, 2012

Implicit Density Estimation by Local Moment Matching to Sample from Auto-Encoders
CoRR, 2012

Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives
CoRR, 2012

Practical recommendations for gradient-based training of deep architectures
CoRR, 2012

On Training Deep Boltzmann Machines
CoRR, 2012

Evolving Culture vs Local Minima
CoRR, 2012

Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery
CoRR, 2012

Detonation Classification from acoustic Signature with the Restricted Boltzmann Machine.
Comput. Intell., 2012

Building Musically-relevant Audio Features through Multiple Timescale Representations.
Proceedings of the 13th International Society for Music Information Retrieval Conference, 2012

Discriminative Non-negative Matrix Factorization for Multiple Pitch Estimation.
Proceedings of the 13th International Society for Music Information Retrieval Conference, 2012

A Generative Process for Contractive Auto-Encoders.
Proceedings of the 29th International Conference on Machine Learning, 2012

Large-Scale Feature Learning With Spike-and-Slab Sparse Coding.
Proceedings of the 29th International Conference on Machine Learning, 2012

Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription.
Proceedings of the 29th International Conference on Machine Learning, 2012

Disentangling Factors of Variation for Facial Expression Recognition.
Proceedings of the Computer Vision - ECCV 2012, 2012

Deep Learning for NLP (without Magic).
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, 2012

2011
Contextual tag inference.
ACM Trans. Multim. Comput. Commun. Appl., 2011

Quickly Generating Representative Samples from an RBM-Derived Process.
Neural Comput., 2011

Suitability of V1 Energy Models for Object Classification.
Neural Comput., 2011

Deep Sparse Rectifier Neural Networks.
Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011

A Spike and Slab Restricted Boltzmann Machine.
Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011

Deep Learners Benefit More from Out-of-Distribution Examples.
Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011

Discussion of "The Neural Autoregressive Distribution Estimator".
Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011

The Statistical Inefficiency of Sparse Coding for Images (or, One Gabor to Rule them All)
CoRR, 2011

Towards Open-Text Semantic Parsing via Multi-Task Learning of Structured Embeddings
CoRR, 2011

Learning invariant features through local space contraction
CoRR, 2011

Adding noise to the input of a model trained with a regularized objective
CoRR, 2011

Autotagging music with conditional restricted Boltzmann machines
CoRR, 2011

Higher Order Contractive Auto-Encoder.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2011

The Manifold Tangent Classifier.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

On Tracking The Partition Function.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

Shallow vs. Deep Sum-Product Networks.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

Algorithms for Hyper-Parameter Optimization.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

On learning distributed representations of semantics.
Proceedings of the 2011 Symposium on Machine Learning in Speech and Language Processing, 2011

Temporal Pooling and Multiscale Learning for Automatic Annotation and Ranking of Music Audio.
Proceedings of the 12th International Society for Music Information Retrieval Conference, 2011

Contractive Auto-Encoders: Explicit Invariance During Feature Extraction.
Proceedings of the 28th International Conference on Machine Learning, 2011

Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach.
Proceedings of the 28th International Conference on Machine Learning, 2011

Large-Scale Learning of Embeddings with Reconstruction Sampling.
Proceedings of the 28th International Conference on Machine Learning, 2011

Unsupervised Models of Images by Spikeand-Slab RBMs.
Proceedings of the 28th International Conference on Machine Learning, 2011

On the Expressive Power of Deep Architectures.
Proceedings of the Algorithmic Learning Theory - 22nd International Conference, 2011

Learning Structured Embeddings of Knowledge Bases.
Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, 2011

2010
Deep Belief Networks Are Compact Universal Approximators.
Neural Comput., 2010

Tractable Multivariate Binary Density Estimation and the Restricted Boltzmann Forest.
Neural Comput., 2010

Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion.
J. Mach. Learn. Res., 2010

Understanding the difficulty of training deep feedforward neural networks.
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010

Why Does Unsupervised Pre-training Help Deep Learning?
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010

Why Does Unsupervised Pre-training Help Deep Learning?
J. Mach. Learn. Res., 2010

Tempered Markov Chain Monte Carlo for training of Restricted Boltzmann Machines.
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010

Alternative time representation in dopamine models.
J. Comput. Neurosci., 2010

Adaptive Parallel Tempering for Stochastic Maximum Likelihood Learning of RBMs
CoRR, 2010

Deep Self-Taught Learning for Handwritten Character Recognition
CoRR, 2010

Decision trees do not generalize to new variations.
Comput. Intell., 2010

Theano: A CPU and GPU Math Compiler in Python.
Proceedings of the 9th Python in Science Conference 2010 (SciPy 2010), Austin, Texas, June 28, 2010

Learning Tags that Vary Within a Song.
Proceedings of the 11th International Society for Music Information Retrieval Conference, 2010

Word Representations: A Simple and General Method for Semi-Supervised Learning.
Proceedings of the ACL 2010, 2010

2009
A Hybrid Pareto Mixture for Conditional Asymmetric Fat-Tailed Distributions.
IEEE Trans. Neural Networks, 2009

Justifying and Generalizing Contrastive Divergence.
Neural Comput., 2009

Exploring Strategies for Training Deep Neural Networks.
J. Mach. Learn. Res., 2009

The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training.
Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics, 2009

Incorporating Functional Knowledge in Neural Networks.
J. Mach. Learn. Res., 2009

Learning Deep Architectures for AI.
Found. Trends Mach. Learn., 2009

An Infinite Factor Model Hierarchy Via a Noisy-Or Mechanism.
Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009

Slow, Decorrelated Features for Pretraining Complex Cell-like Networks.
Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009

Quadratic Features and Deep Architectures for Chunking.
Proceedings of the Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings, May 31, 2009

Workshop summary: Workshop on learning feature hierarchies.
Proceedings of the 26th Annual International Conference on Machine Learning, 2009

Curriculum learning.
Proceedings of the 26th Annual International Conference on Machine Learning, 2009

2008
Adaptive Importance Sampling to Accelerate Training of a Neural Probabilistic Language Model.
IEEE Trans. Neural Networks, 2008

Neural net language models.
Scholarpedia, 2008

Representational Power of Restricted Boltzmann Machines and Deep Belief Networks.
Neural Comput., 2008

Extracting and composing robust features with denoising autoencoders.
Proceedings of the Machine Learning, 2008

Classification using discriminative restricted Boltzmann machines.
Proceedings of the Machine Learning, 2008

Zero-data Learning of New Tasks.
Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence, 2008

2007
Continuous Neural Networks.
Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics, 2007

A Hybrid Pareto Model for Conditional Density Estimation of Asymmetric Fat-Tail Data.
Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics, 2007

Noisy K Best-Paths for Approximate Dynamic Programming with Application to Portfolio Optimization.
J. Comput., 2007

Topmoumoute Online Natural Gradient Algorithm.
Proceedings of the Advances in Neural Information Processing Systems 20, 2007

Learning the 2-D Topology of Images.
Proceedings of the Advances in Neural Information Processing Systems 20, 2007

Augmented Functional Time Series Representation and Forecasting with Gaussian Processes.
Proceedings of the Advances in Neural Information Processing Systems 20, 2007

An empirical evaluation of deep architectures on problems with many factors of variation.
Proceedings of the Machine Learning, 2007

2006
Nonlocal Estimation of Manifold Structure.
Neural Comput., 2006

Collaborative Filtering on a Family of Biological Targets.
J. Chem. Inf. Model., 2006

Greedy Layer-Wise Training of Deep Networks.
Proceedings of the Advances in Neural Information Processing Systems 19, 2006

The <i>K</i> Best-Paths Approach to Approximate Dynamic Programming with Application to Portfolio Optimization.
Proceedings of the Advances in Artificial Intelligence, 2006

Spectral Dimensionality Reduction.
Proceedings of the Feature Extraction - Foundations and Applications, 2006

Entropy Regularization.
Proceedings of the Semi-Supervised Learning, 2006

Large-Scale Algorithms.
Proceedings of the Semi-Supervised Learning, 2006

Label Propagation and Quadratic Criterion.
Proceedings of the Semi-Supervised Learning, 2006

2005
Convex Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, 2005

Non-Local Manifold Parzen Windows.
Proceedings of the Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, 2005

The Curse of Highly Variable Functions for Local Kernel Machines.
Proceedings of the Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, 2005

Greedy Spectral Embedding.
Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, 2005

Hierarchical Probabilistic Neural Network Language Model.
Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, 2005

Efficient Non-Parametric Function Induction in Semi-Supervised Learning.
Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, 2005

2004
Learning Eigenfunctions Links Spectral Embedding and Kernel PCA.
Neural Comput., 2004

No Unbiased Estimator of the Variance of K-Fold Cross-Validation.
J. Mach. Learn. Res., 2004

Locally Linear Embedding for dimensionality reduction in QSAR.
J. Comput. Aided Mol. Des., 2004

Approche statistique pour le repérage de mots informatifs dans les textes oraux.
Proceedings of the Actes de la 11ème conférence sur le Traitement Automatique des Langues Naturelles. Articles longs, 2004

Brain Inspired Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, 2004

Semi-supervised Learning by Entropy Minimization.
Proceedings of the Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, 2004

Non-Local Manifold Tangent Learning.
Proceedings of the Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, 2004

Unsupervised Sense Disambiguation Using Bilingual Probabilistic Models.
Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, 2004

2003
Bias learning, knowledge sharing.
IEEE Trans. Neural Networks, 2003

Inference for the Generalization Error.
Mach. Learn., 2003

A Neural Probabilistic Language Model.
J. Mach. Learn. Res., 2003

Extensions to Metric-Based Model Selection.
J. Mach. Learn. Res., 2003

Scaling Large Learning Problems with Hard Parallel Mixtures.
Int. J. Pattern Recognit. Artif. Intell., 2003

Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering.
Proceedings of the Advances in Neural Information Processing Systems 16 [Neural Information Processing Systems, 2003

Quick Training of Probabilistic Neural Nets by Importance Sampling.
Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, 2003

2002
Robust Regression with Asymmetric Heavy-Tail Noise Distributions.
Neural Comput., 2002

A Parallel Mixture of SVMs for Very Large Scale Problems.
Neural Comput., 2002

Kernel Matching Pursuit.
Mach. Learn., 2002

Model Selection for Small Sample Regression.
Mach. Learn., 2002

Guest Introduction: Special Issue on New Methods for Model Selection and Model Combination.
Mach. Learn., 2002

Segmentation en thèmes de conversations téléphoniques : traitement en amont pour l'extraction d'information.
Proceedings of the Actes de la 9ème conférence sur le Traitement Automatique des Langues Naturelles. Posters, 2002

Metric-based model selection for time-series forecasting.
Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing, 2002

Manifold Parzen Windows.
Proceedings of the Advances in Neural Information Processing Systems 15 [Neural Information Processing Systems, 2002

2001
Cost functions and model combination for VaR-based asset allocation using neural networks.
IEEE Trans. Neural Networks, 2001

Experiments on the application of IOHMMs to model financial returns series.
IEEE Trans. Neural Networks, 2001

Topic Segmentation : A First Stage to Dialog-Based Information Extraction.
Proceedings of the Sixth Natural Language Processing Pacific Rim Symposium, 2001

K-Local Hyperplane and Convex Distance Nearest Neighbor Algorithms.
Proceedings of the Advances in Neural Information Processing Systems 14 [Neural Information Processing Systems: Natural and Synthetic, 2001

Estimating Car Insurance Premia: a Case Study in High-Dimensional Data Inference.
Proceedings of the Advances in Neural Information Processing Systems 14 [Neural Information Processing Systems: Natural and Synthetic, 2001

2000
Taking on the curse of dimensionality in joint distributions using neural networks.
IEEE Trans. Neural Networks Learn. Syst., 2000

Boosting Neural Networks.
Neural Comput., 2000

Gradient-Based Optimization of Hyperparameters.
Neural Comput., 2000

Incorporating Second-Order Functional Knowledge for Better Option Pricing.
Proceedings of the Advances in Neural Information Processing Systems 13, 2000

A Neural Probabilistic Language Model.
Proceedings of the Advances in Neural Information Processing Systems 13, 2000

A Neural Support Vector Network Architecture with Adaptive Kernels.
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000

Probabilistic Neural Network Models for Sequential Data.
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000

Continuous Optimization of Hyper-Parameters.
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000

1999
Stochastic Learning of Strategic Equilibria for Auctions.
Neural Comput., 1999

Object Recognition with Gradient-Based Learning.
Proceedings of the Shape, Contour and Grouping in Computer Vision, 1999

Modeling High-Dimensional Discrete Data with Multi-Layer Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 12, [NIPS Conference, Denver, Colorado, USA, November 29, 1999

Binary Pseudowavelets and Applications to Bilevel Image Processing.
Proceedings of the Data Compression Conference, 1999

1998
Gradient-based learning applied to document recognition.
Proc. IEEE, 1998

High quality document image compression with "DjVu".
J. Electronic Imaging, 1998

Gaussian Mixture Densities for Classification of Nuclear Power Plant Data.
Comput. Artif. Intell., 1998

Support vector machines for improving the classification of brain PET images.
Proceedings of the Medical Imaging 1998: Image Processing, 1998

A Memory-Efficient Adaptive Huffman Coding Algorthm for Very Large Sets of Symbols.
Proceedings of the Data Compression Conference, 1998

The Z-Coder Adaptive Binary Coder.
Proceedings of the Data Compression Conference, 1998

Browsing through High Quality Document Images with DjVu.
Proceedings of the IEEE Forum on Research and Technology Advances in Digital Libraries, 1998

1997
Using a Financial Training Criterion Rather than a Prediction Criterion.
Int. J. Neural Syst., 1997

Training Methods for Adaptive Boosting of Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 10, 1997

Shared Context Probabilistic Transducers.
Proceedings of the Advances in Neural Information Processing Systems 10, 1997

Discriminative feature and model design for automatic speech recognition.
Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Reading checks with multilayer graph transformer networks.
Proceedings of the 1997 IEEE International Conference on Acoustics, 1997

AdaBoosting Neural Networks: Application to on-line Character Recognition.
Proceedings of the Artificial Neural Networks, 1997

Global Training of Document Processing Systems Using Graph Transformer Networks.
Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97), 1997

1996
Input-output HMMs for sequence processing.
IEEE Trans. Neural Networks, 1996

Multi-Task Learning for Stock Selection.
Proceedings of the Advances in Neural Information Processing Systems 9, 1996

1995
On the search for new learning rules for ANNs.
Neural Process. Lett., 1995

LeRec: a NN/HMM hybrid for on-line handwriting recognition.
Neural Comput., 1995

Diffusion of Context and Credit Information in Markovian Models.
J. Artif. Intell. Res., 1995

Hierarchical Recurrent Neural Networks for Long-Term Dependencies.
Proceedings of the Advances in Neural Information Processing Systems 8, 1995

Recurrent Neural Networks for Missing or Asynchronous Data.
Proceedings of the Advances in Neural Information Processing Systems 8, 1995

1994
Learning long-term dependencies with gradient descent is difficult.
IEEE Trans. Neural Networks, 1994

Convergence Properties of the K-Means Algorithms.
Proceedings of the Advances in Neural Information Processing Systems 7, 1994

Diffusion of Credit in Markovian Models.
Proceedings of the Advances in Neural Information Processing Systems 7, 1994

An Input Output HMM Architecture.
Proceedings of the Advances in Neural Information Processing Systems 7, 1994

Word-level training of a handwritten word recognizer based on convolutional neural networks.
Proceedings of the 12th IAPR International Conference on Pattern Recognition, 1994

An EM approach to grammatical inference: input/output HMMs.
Proceedings of the 12th IAPR International Conference on Pattern Recognition, 1994

Word normalization for online handwritten word recognition.
Proceedings of the 12th IAPR International Conference on Pattern Recognition, 1994

Use of Genetic Programming for the Search of a New Learning Rule for Neural Networks.
Proceedings of the First IEEE Conference on Evolutionary Computation, 1994

1993
A Connectionist Approach to Speech Recognition.
Int. J. Pattern Recognit. Artif. Intell., 1993

Credit Assignment through Time: Alternatives to Backpropagation.
Proceedings of the Advances in Neural Information Processing Systems 6, 1993

Globally Trained Handwritten Word Recognizer Using Spatial Representation, Convolutional Neural Networks, and Hidden Markov Models.
Proceedings of the Advances in Neural Information Processing Systems 6, 1993

The problem of learning long-term dependencies in recurrent networks.
Proceedings of International Conference on Neural Networks (ICNN'88), San Francisco, CA, USA, March 28, 1993

1992
Global optimization of a neural network-hidden Markov model hybrid.
IEEE Trans. Neural Networks, 1992

Phonetically motivated acoustic parameters for continuous speech recognition using artificial neural networks.
Speech Commun., 1992

Learning the dynamic nature of speech with back-propagation for sequences.
Pattern Recognit. Lett., 1992

1991
Neural Network - Gaussian Mixture Hybrid for Speech Recognition or Density Estimation.
Proceedings of the Advances in Neural Information Processing Systems 4, 1991

A comparative study on hybrid acoustic phonetic decoders based on artificial neural networks.
Proceedings of the Second European Conference on Speech Communication and Technology, 1991

1990
Phonetically-based multi-layered neural networks for vowel classification.
Speech Commun., 1990

Efficient recognition of immunoglobulin domains from amino acid sequences using a neural network.
Comput. Appl. Biosci., 1990

A hybrid coder for hidden Markov models using a recurrent neural network.
Proceedings of the 1990 International Conference on Acoustics, 1990

1989
Programmable Execution of Multi-Layered Networks for Automatic Speech Recognition.
Commun. ACM, 1989

Speaker Independent Speech Recognition with Neural Networks and Speech Knowledge.
Proceedings of the Advances in Neural Information Processing Systems 2, 1989

A Neural Network to Detect Homologies in Proteins.
Proceedings of the Advances in Neural Information Processing Systems 2, 1989

Speech coding with multilayer networks.
Proceedings of the Neurocomputing - Algorithms, Architectures and Applications, Proceedings of the NATO Advanced Research Workshop on Neurocomputing Algorithms, Architectures and Applications, Les Arcs, France, February 27, 1989

On the Generalization Capability of Multi-Layered Networks in the Extraction of Speech Properties.
Proceedings of the 11th International Joint Conference on Artificial Intelligence. Detroit, 1989

Speech coding with multi-layer networks.
Proceedings of the IEEE International Conference on Acoustics, 1989

1988
Use of Multi-Layered Networks for Coding Speech with Phonetic Features.
Proceedings of the Advances in Neural Information Processing Systems 1, 1988

Use of neural networks for the recognition of place of articulation.
Proceedings of the IEEE International Conference on Acoustics, 1988

Data-Driven Execution of Multi-Layered Networks for Automatic Speech Recognition.
Proceedings of the 7th National Conference on Artificial Intelligence, 1988


  Loading...